2 * SARG Squid Analysis Report Generator http://sarg.sourceforge.net
6 * please look at http://sarg.sourceforge.net/donations.php
8 * http://sourceforge.net/projects/sarg/forums/forum/363374
9 * ---------------------------------------------------------------------
11 * This program is free software; you can redistribute it and/or modify
12 * it under the terms of the GNU General Public License as published by
13 * the Free Software Foundation; either version 2 of the License, or
14 * (at your option) any later version.
16 * This program is distributed in the hope that it will be useful,
17 * but WITHOUT ANY WARRANTY; without even the implied warranty of
18 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 * GNU General Public License for more details.
21 * You should have received a copy of the GNU General Public License
22 * along with this program; if not, write to the Free Software
23 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
27 #include "include/conf.h"
28 #include "include/defs.h"
30 static char **files_done
= NULL
;
31 static int nfiles_done
= 0;
33 //! The number of invalid lines found in the redirector report.
34 static int RedirectorErrors
=0;
35 //! The file containing the sorted entries.
36 static char redirector_sorted
[MAXLEN
]="";
38 static void parse_log(FILE *fp_ou
,char *buf
)
40 char leks
[5], sep
[2], res
[MAXLEN
];
42 char source
[128], list
[128];
43 char full_url
[MAX_URL_LEN
];
45 char user
[MAX_USER_LEN
];
47 long long int lmon
, lday
, lyear
;
51 struct getwordstruct gwarea
;
52 struct getwordstruct gwarea1
;
53 struct userinfostruct
*uinfo
;
55 getword_start(&gwarea
,buf
);
56 if(RedirectorLogFormat
[0] != '\0') {
57 getword_start(&gwarea1
,RedirectorLogFormat
);
59 if (getword(leks
,sizeof(leks
),&gwarea1
,'#')<0) {
60 debuga(_("Invalid \"redirector_log_format\" option in your sarg.conf (too many characters before first tag)\n"));
72 while(strcmp(leks
,"end") != 0) {
73 if (getword(leks
,sizeof(leks
),&gwarea1
,'#')<0) {
74 debuga(_("Invalid \"redirector_log_format\" option in your sarg.conf (missing # at end of tag)\n"));
77 if (getword(sep
,sizeof(sep
),&gwarea1
,'#')<0) {
78 debuga(_("Invalid \"redirector_log_format\" option in your sarg.conf (too many characters in column separator)\n"));
81 if(strcmp(leks
,"end") != 0) {
82 if (getword_limit(res
,sizeof(res
),&gwarea
,sep
[0])<0) {
83 debuga(_("Parsing of tag \"%s\" in redirector log %s returned no result\n"),leks
,wentp
);
87 if(strcmp(leks
,"year") == 0) {
89 } else if(strcmp(leks
,"mon") == 0) {
91 } else if(strcmp(leks
,"day") == 0) {
93 } else if(strcmp(leks
,"hour") == 0) {
94 if (strlen(res
)>=sizeof(hour
)) {
95 debuga(_("Hour string too long in redirector log file %s\n"),wentp
);
100 } else if(strcmp(leks
,"source") == 0) {
101 if (strlen(res
)>=sizeof(source
)) {
102 debuga(_("Banning source name too long in redirector log file %s\n"),wentp
);
107 } else if(strcmp(leks
,"list") == 0) {
108 if (strlen(res
)>=sizeof(list
)) {
109 debuga(_("Banning list name too long in redirector log file %s\n"),wentp
);
114 } else if(strcmp(leks
,"ip") == 0) {
115 if (strlen(res
)>=sizeof(ip
)) {
116 debuga(_("IP address too long in redirector log file %s\n"),wentp
);
121 } else if(strcmp(leks
,"user") == 0) {
122 if (strlen(res
)>=sizeof(user
)) {
123 debuga(_("User ID too long in redirector log file %s\n"),wentp
);
128 } else if(strcmp(leks
,"url") == 0) {
130 * Don't worry about the url being truncated as we only keep the host name
133 safe_strcpy(full_url
,res
,sizeof(full_url
));
138 if (getword_atoll(&lyear
,&gwarea
,'-')<0 || getword_atoll(&lmon
,&gwarea
,'-')<0 ||
139 getword_atoll(&lday
,&gwarea
,' ')<0) {
140 debuga(_("Invalid date found in file %s\n"),wentp
);
147 if (getword(hour
,sizeof(hour
),&gwarea
,' ')<0) {
148 debuga(_("Invalid time found in file %s\n"),wentp
);
152 if (getword_skip(MAXLEN
,&gwarea
,'(')<0 || getword(source
,sizeof(source
),&gwarea
,'/')<0) {
153 debuga(_("Invalid redirected source in file %s\n"),wentp
);
157 if (getword(list
,sizeof(list
),&gwarea
,'/')<0) {
158 debuga(_("Invalid redirected list in file %s\n"),wentp
);
162 if (getword_skip(MAXLEN
,&gwarea
,' ')<0 || getword_limit(full_url
,sizeof(full_url
),&gwarea
,' ')<0) {
163 debuga(_("Invalid URL in file %s\n"),wentp
);
167 if (getword(ip
,sizeof(ip
),&gwarea
,'/')<0) {
168 debuga(_("Invalid source IP in file %s\n"),wentp
);
172 if (getword_skip(MAXLEN
,&gwarea
,' ')<0 || getword(user
,sizeof(user
),&gwarea
,' ')<0) {
173 debuga(_("Invalid user in file %s\n"),wentp
);
178 url
=process_url(full_url
,false);
180 //sprintf(warea,"%04d%02d%02d",year,mon,day);
182 if(RedirectorFilterOutDate
) {
183 idata
= year
*10000+mon
*100+day
;
184 if(idata
< dfrom
|| idata
> duntil
)
193 if (user
[0]=='\0' || (user
[1]=='\0' && (user
[0]=='-' || user
[0]==' '))) {
194 if(RecordsWithoutUser
== RECORDWITHOUTUSER_IP
) {
198 if(RecordsWithoutUser
== RECORDWITHOUTUSER_IGNORE
)
200 if(RecordsWithoutUser
== RECORDWITHOUTUSER_EVERYBODY
)
201 strcpy(user
,"everybody");
204 uinfo
=userinfo_find_from_id(user
);
206 uinfo
=userinfo_create(user
);
207 uinfo
->id_is_ip
=id_is_ip
;
208 uinfo
->no_report
=true;
209 if(Ip2Name
&& id_is_ip
) ip2name(user
,sizeof(user
));
210 user_find(uinfo
->label
,MAX_USER_LEN
, user
);
212 fprintf(fp_ou
,"%s\t%04d%02d%02d\t%s\t%s\t%s\t",uinfo
->id
,year
,mon
,day
,hour
,ip
,url
);
213 if (source
[0] && list
[0])
214 fprintf(fp_ou
,"%s/%s\n",source
,list
);
216 fprintf(fp_ou
,"%s\n",source
);
218 fprintf(fp_ou
,"%s\n",list
);
222 static void read_log(const char *wentp
, FILE *fp_ou
,int dfrom
,int duntil
)
230 debuga(_("Reading redirector log file %s\n"),wentp
);
233 /* With squidGuard, you can log groups in only one log file.
234 We must parse each log files only one time. Example :
236 domainlist porn/domains
241 domainlist aggressive/domains
242 urllist aggressive/urls
246 domainlist audio-video/domains
247 urllist audio-video/urls
251 for (i
=0; i
<nfiles_done
; i
++)
252 if (!strcmp(wentp
, files_done
[i
])) return;
255 files_done
= realloc(files_done
, nfiles_done
*sizeof(char *));
257 debuga(_("Not enough memory to store the name of the new redirector log to be read - %s\n"),strerror(errno
));
260 files_done
[nfiles_done
-1] = strdup(wentp
);
261 if (!files_done
[nfiles_done
-1]) {
262 debuga(_("Not enough memory to store the name of the new redirector log to be read - %s\n"),strerror(errno
));
266 if ((fp_in
=fopen(wentp
,"r"))==NULL
) {
267 debuga(_("(squidguard) Cannot open log file %s: %s\n"),wentp
,strerror(errno
));
271 if ((line
=longline_create())==NULL
) {
272 debuga(_("Not enough memory to read the redirector log\n"));
276 while ((buf
=longline_read(fp_in
,line
)) != NULL
) {
277 parse_log(fp_ou
,buf
);
280 longline_destroy(&line
);
285 void redirector_log(void)
287 FILE *fp_ou
= NULL
, *fp_guard
= NULL
;
289 char guard_in
[MAXLEN
];
302 if(SquidGuardConf
[0] == '\0' && NRedirectorLogs
== 0) {
303 if (debugz
) debugaz(_("No redirector logs provided to produce that kind of report\n"));
307 snprintf(guard_in
,sizeof(guard_in
),"%s/redirector.int_unsort",tmp
);
308 if((fp_ou
=fopen(guard_in
,"w"))==NULL
) {
309 debuga(_("(squidguard) Cannot open log file %s: %s\n"),guard_in
,strerror(errno
));
313 dfrom
=(period
.start
.tm_year
+1900)*10000+(period
.start
.tm_mon
+1)*100+period
.start
.tm_mday
;
314 duntil
=(period
.end
.tm_year
+1900)*10000+(period
.end
.tm_mon
+1)*100+period
.end
.tm_mday
;
316 if (NRedirectorLogs
>0) {
317 for (i
=0 ; i
<NRedirectorLogs
; i
++)
318 read_log(RedirectorLogs
[i
],fp_ou
,dfrom
,duntil
);
320 if(access(SquidGuardConf
, R_OK
) != 0) {
321 debuga(_("Cannot open squidGuard config file: %s\n"),SquidGuardConf
);
325 if((fp_guard
=fopen(SquidGuardConf
,"r"))==NULL
) {
326 debuga(_("(squidguard) Cannot open log file %s: %s\n"),SquidGuardConf
,strerror(errno
));
331 while(fgets(buf
,sizeof(buf
),fp_guard
)!=NULL
) {
333 if((str
=get_param_value("logdir",buf
))!=NULL
) {
335 We want to tolerate spaces inside the directory name but we must also
336 remove the trailing spaces left by the editor after the directory name.
337 This should not be a problem as nobody use a file name with trailing spaces.
339 for (y
=strlen(str
)-1 ; y
>=0 && (unsigned char)str
[y
]<=' ' ; y
--);
340 if (y
>=sizeof(logdir
)-1) y
=sizeof(logdir
)-2;
346 } else if((str
=get_param_value("log",buf
))!=NULL
) {
347 if((str2
=get_param_value("anonymous",str
))!=NULL
)
351 If logdir is defined, we prepend it to the log file name, otherwise, we assume
352 the log directive provides an absolute file name to the log file. Therefore,
353 we don't need to add an additionnal / at the beginning of the log file name.
355 y
=(logdir
[0]) ? sprintf(wentp
,"%s/",logdir
) : 0;
357 Spaces are allowed in the name of the log file. The file name ends at the first #
358 because it is assumed it is an end of line comment. Any space before the # is then
359 removed. Any control character (i.e. a character with a code lower than 32) ends
360 the file name. That includes the terminating zero.
362 while((unsigned char)*str
>=' ' && *str
!='#' && y
<sizeof(wentp
)-1)
366 while(*str
==' ' && y
>0) {
372 read_log(wentp
,fp_ou
,dfrom
,duntil
);
377 if (fp_guard
) fclose(fp_guard
);
378 if (fp_ou
) fclose(fp_ou
);
381 for (y
=0; y
<nfiles_done
; y
++)
382 if (files_done
[y
]) free(files_done
[y
]);
386 if (redirector_count
) {
387 snprintf(redirector_sorted
,sizeof(redirector_sorted
),"%s/redirector.int_log",tmp
);
389 debuga(_("Sorting file: %s\n"),redirector_sorted
);
392 if (snprintf(tmp6
,sizeof(tmp6
),"sort -t \"\t\" -k 1,1 -k 2,2 -k 4,4 \"%s\" -o \"%s\"",guard_in
, redirector_sorted
)>=sizeof(tmp6
)) {
393 debuga(_("Sort command too long when sorting file \"%s\" to \"%s\"\n"),guard_in
,redirector_sorted
);
396 cstatus
=system(tmp6
);
397 if (!WIFEXITED(cstatus
) || WEXITSTATUS(cstatus
)) {
398 debuga(_("sort command return status %d\n"),WEXITSTATUS(cstatus
));
399 debuga(_("sort command: %s\n"),tmp6
);
404 if (!KeepTempLog
&& unlink(guard_in
)) {
405 debuga(_("Cannot delete \"%s\": %s\n"),guard_in
,strerror(errno
));
411 static void show_ignored_redirector(FILE *fp_ou
,int count
)
415 snprintf(ignored
,sizeof(ignored
),ngettext("%d more redirector entry not shown here…","%d more redirector entries not shown here…",count
),count
);
416 fprintf(fp_ou
,"<tr><td class=\"data\"></td><td class=\"data\"></td><td class=\"data\"></td><td class=\"data2 more\">%s</td><td class=\"data\"></td></tr>\n",ignored
);
419 void redirector_report(void)
421 FILE *fp_in
= NULL
, *fp_ou
= NULL
;
439 struct getwordstruct gwarea
;
440 const struct userinfostruct
*uinfo
;
447 if(!redirector_count
) {
449 if (redirector_sorted
[0])
450 debugaz(_("Redirector report not generated because it is empty\n"));
455 snprintf(report
,sizeof(report
),"%s/redirector.html",outdirname
);
457 if((fp_in
=fopen(redirector_sorted
,"r"))==NULL
) {
458 debuga(_("(squidguard) Cannot open log file %s: %s\n"),redirector_sorted
,strerror(errno
));
462 if((fp_ou
=fopen(report
,"w"))==NULL
) {
463 debuga(_("(squidguard) Cannot open log file %s: %s\n"),report
,strerror(errno
));
467 if ((line
=longline_create())==NULL
) {
468 debuga(_("Not enough memory to read the processed redirector log\n"));
472 write_html_header(fp_ou
,(IndexTree
== INDEX_TREE_DATE
) ? 3 : 1,_("Redirector report"),HTML_JS_NONE
);
473 fputs("<tr><td class=\"header_c\">",fp_ou
);
474 fprintf(fp_ou
,_("Period: %s"),period
.html
);
475 fputs("</td></tr>\n",fp_ou
);
476 fprintf(fp_ou
,"<tr><th class=\"header_c\">%s</th></tr>\n",_("Redirector report"));
477 close_html_header(fp_ou
);
479 fputs("<div class=\"report\"><table cellpadding=1 cellspacing=2>\n",fp_ou
);
480 fprintf(fp_ou
,"<tr><th class=\"header_l\">%s</th><th class=\"header_l\">%s</th><th class=\"header_l\">%s</th><th class=\"header_l\">%s</th><th class=\"header_l\">%s</th></tr>\n",_("USERID"),_("IP/NAME"),_("DATE/TIME"),_("ACCESSED SITE"),_("RULE"));
482 while((buf
=longline_read(fp_in
,line
))!=NULL
) {
483 getword_start(&gwarea
,buf
);
484 if (getword(user
,sizeof(user
),&gwarea
,'\t')<0) {
485 debuga(_("Invalid user in file %s\n"),redirector_sorted
);
488 if (getword_atoll(&data2
,&gwarea
,'\t')<0) {
489 debuga(_("Invalid date in file %s\n"),redirector_sorted
);
492 if (getword(hora
,sizeof(hora
),&gwarea
,'\t')<0) {
493 debuga(_("Invalid time in file %s\n"),redirector_sorted
);
496 if (getword(ip
,sizeof(ip
),&gwarea
,'\t')<0) {
497 debuga(_("Invalid IP address in file %s\n"),redirector_sorted
);
500 if (getword_ptr(buf
,&url
,&gwarea
,'\t')<0) {
501 debuga(_("Invalid URL in file %s\n"),redirector_sorted
);
504 if (getword(rule
,sizeof(rule
),&gwarea
,'\n')<0) {
505 debuga(_("Invalid rule in file %s\n"),redirector_sorted
);
509 uinfo
=userinfo_find_from_id(user
);
511 debuga(_("Unknown user ID %s in file %s\n"),user
,redirector_sorted
);
515 computedate(data2
/10000,(data2
/100)%10,data2
%100,&t
);
516 strftime(data
,sizeof(data
),"%x",&t
);
523 if (Ip2Name
&& !uinfo
->id_is_ip
) ip2name(oname
,sizeof(oname
));
527 if(strcmp(ouser
,user
) != 0) {
531 if(strcmp(oip
,ip
) != 0) {
534 if (Ip2Name
&& !uinfo
->id_is_ip
) ip2name(oname
,sizeof(oname
));
539 if(SquidGuardReportLimit
) {
540 if(strcmp(ouser2
,uinfo
->label
) == 0) {
543 if(count
>SquidGuardReportLimit
&& SquidGuardReportLimit
>0)
544 show_ignored_redirector(fp_ou
,count
-SquidGuardReportLimit
);
546 strcpy(ouser2
,uinfo
->label
);
548 if(count
> SquidGuardReportLimit
)
553 fprintf(fp_ou
,"<tr><td class=\"data2\">%s</td><td class=\"data2\">%s</td>",uinfo
->label
,ip
);
555 fputs("<tr><td class=\"data2\"></td><td class=\"data2\"></td>",fp_ou
);
556 fprintf(fp_ou
,"<td class=\"data2\">%s-%s</td><td class=\"data2\">",data
,hora
);
557 output_html_link(fp_ou
,url
,100);
558 fprintf(fp_ou
,"</td><td class=\"data2\">%s</td></tr>\n",rule
);
561 longline_destroy(&line
);
563 if(count
>SquidGuardReportLimit
&& SquidGuardReportLimit
>0)
564 show_ignored_redirector(fp_ou
,count
-SquidGuardReportLimit
);
566 fputs("</table>\n",fp_ou
);
568 if (RedirectorErrors
>0)
570 fputs("<div class=\"warn\"><span>",fp_ou
);
571 fprintf(fp_ou
,ngettext("%d error found in the log file. Some entries may be missing.","%d errors found in the log file. Some entries may be missing.",RedirectorErrors
),RedirectorErrors
);
572 fputs("</span></div>\n",fp_ou
);
575 fputs("</div>\n",fp_ou
);
576 if (write_html_trailer(fp_ou
)<0)
577 debuga(_("Write error in file %s\n"),report
);
578 if (fclose(fp_ou
)==EOF
)
579 debuga(_("Failed to close file %s - %s\n"),report
,strerror(errno
));
581 if (!KeepTempLog
&& unlink(redirector_sorted
)) {
582 debuga(_("Cannot delete \"%s\": %s\n"),redirector_sorted
,strerror(errno
));